fix: refine narrative schema pack #19501
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,104 @@ | ||
| { | ||
| "$schema": "https://json-schema.org/draft/2020-12/schema", | ||
| "$id": "https://summit.example.com/schemas/provenance/receipt.schema.json", | ||
| "title": "ProvenanceReceipt", | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": [ | ||
| "version", | ||
| "provenance_id", | ||
| "generated_by", | ||
| "inputs", | ||
| "transforms", | ||
| "outputs" | ||
| ], | ||
| "properties": { | ||
| "version": { | ||
| "type": "string", | ||
| "minLength": 1 | ||
| }, | ||
| "provenance_id": { | ||
| "type": "string", | ||
| "pattern": "^sha256:[a-f0-9]{64}$" | ||
| }, | ||
| "generated_by": { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": [ | ||
| "pipeline", | ||
| "pipeline_version", | ||
| "model", | ||
| "model_version", | ||
| "policy_version" | ||
| ], | ||
| "properties": { | ||
| "pipeline": {"type": "string", "minLength": 1}, | ||
| "pipeline_version": {"type": "string", "minLength": 1}, | ||
| "model": {"type": "string", "minLength": 1}, | ||
| "model_version": {"type": "string", "minLength": 1}, | ||
| "policy_version": {"type": "string", "minLength": 1} | ||
| } | ||
| }, | ||
| "inputs": { | ||
| "type": "array", | ||
| "minItems": 1, | ||
| "items": { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": ["artifact_id", "content_hash"], | ||
| "properties": { | ||
| "artifact_id": { | ||
| "type": "string", | ||
| "pattern": "^sha256:[a-f0-9]{64}$" | ||
| }, | ||
| "content_hash": { | ||
| "type": "string", | ||
| "pattern": "^sha256:[a-f0-9]{64}$" | ||
| }, | ||
| "span": {"type": "string"} | ||
| } | ||
| } | ||
| }, | ||
| "transforms": { | ||
| "type": "array", | ||
| "minItems": 1, | ||
| "items": { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": ["name", "hash"], | ||
| "properties": { | ||
| "name": {"type": "string", "minLength": 1}, | ||
| "hash": { | ||
| "type": "string", | ||
| "pattern": "^sha256:[a-f0-9]{64}$" | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "outputs": { | ||
| "type": "array", | ||
| "minItems": 1, | ||
| "items": { | ||
| "type": "object", | ||
| "additionalProperties": false, | ||
| "required": ["type", "id", "confidence", "normal_form"], | ||
| "properties": { | ||
| "type": { | ||
| "type": "string", | ||
| "enum": ["Claim", "Frame", "Assumption"] | ||
| }, | ||
| "id": { | ||
| "type": "string", | ||
| "pattern": "^sha256:[a-f0-9]{64}$" | ||
| }, | ||
| "confidence": { | ||
| "type": "number", | ||
| "minimum": 0, | ||
| "maximum": 1 | ||
| }, | ||
| "normal_form": {"type": "string", "minLength": 1} | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,198 @@ | ||
| version: 1 | ||
| namespace: summit.narratives | ||
| id_policy: | ||
| algo: sha256 | ||
| canonicalization: unicode_nfkc_whitespace_collapse | ||
| nodes: | ||
| Artifact: | ||
| description: Observed content item (post/article/video transcript chunk) | ||
| keys: [artifact_id] | ||
| props: | ||
| artifact_id: {type: string, required: true} | ||
| uri: {type: string, required: false} | ||
| platform: {type: string, required: false} | ||
| content_hash: {type: string, required: true} | ||
| lang: {type: string, required: false} | ||
| text_excerpt: {type: string, required: false} | ||
| media_type: {type: string, required: false} # text|image|video|audio|mixed | ||
| collected_at_ref: {type: string, required: false} # pointer to stamp.json record | ||
| integrity: | ||
| type: object | ||
| required: false | ||
| shape: | ||
| hash_algo: {type: string} | ||
| hash: {type: string} | ||
| size_bytes: {type: integer} | ||
|
Comment on lines
+23
to
+25
Contributor
There was a problem hiding this comment. The properties hash_algo: {type: string, required: true}
hash: {type: string, required: true}
size_bytes: {type: integer, required: true} |
||
| Actor: | ||
| keys: [actor_id] | ||
| props: | ||
| actor_id: {type: string, required: true} | ||
| handle: {type: string, required: false} | ||
| display_name: {type: string, required: false} | ||
| actor_type: {type: string, required: false} # individual|org|media|bot_suspected|unknown | ||
| tier: {type: string, required: false} # fringe|influencer|semi_legit|mainstream|official | ||
| Narrative: | ||
| keys: [narrative_id] | ||
| props: | ||
| narrative_id: {type: string, required: true} | ||
| label: {type: string, required: false} | ||
| state: {type: string, required: true} # seeded|contested|normalized|institutionalized|exhausted|dormant|reactivated | ||
| first_seen_ref: {type: string, required: false} | ||
| last_seen_ref: {type: string, required: false} | ||
| topic_tags: {type: list, items: string, required: false} | ||
| Frame: | ||
| keys: [frame_id] | ||
| props: | ||
| frame_id: {type: string, required: true} | ||
| narrative_id: {type: string, required: true} | ||
| frame_normal_form: {type: string, required: true} | ||
| polarity_target: {type: string, required: false} | ||
| solution_hook: {type: string, required: false} | ||
| Claim: | ||
| keys: [claim_id] | ||
| props: | ||
| claim_id: {type: string, required: true} | ||
| claim_normal_form: {type: string, required: true} | ||
| verifiability: {type: string, required: false} # verifiable|nonverifiable|normative|question | ||
| stance: {type: string, required: false} # assert|deny|question|imply | ||
| Assumption: | ||
| keys: [assumption_id] | ||
| props: | ||
| assumption_id: {type: string, required: true} | ||
| assumption_normal_form: {type: string, required: true} | ||
| scope: {type: string, required: false} # local|narrative|cross_narrative | ||
| Community: | ||
| keys: [community_id] | ||
| props: | ||
| community_id: {type: string, required: true} | ||
| method: {type: string, required: false} # louvain|leiden|labelprop|manual | ||
| label: {type: string, required: false} | ||
| Event: | ||
| keys: [event_id] | ||
| props: | ||
| event_id: {type: string, required: true} | ||
| event_type: {type: string, required: false} | ||
| summary: {type: string, required: false} | ||
| time_ref: {type: string, required: false} | ||
| Evidence: | ||
| keys: [evidence_id] | ||
| props: | ||
| evidence_id: {type: string, required: true} | ||
| evidence_type: {type: string, required: false} # report|dataset|factcheck|official_statement|doc | ||
| uri: {type: string, required: false} | ||
| excerpt: {type: string, required: false} | ||
|
|
||
| relationships: | ||
| PUBLISHED: | ||
| from: Actor | ||
| to: Artifact | ||
| props: | ||
| published_ref: {type: string, required: false} | ||
| IN_COMMUNITY: | ||
| from: Actor | ||
| to: Community | ||
| props: {} | ||
| MENTIONS: | ||
| from: Artifact | ||
| to: Actor | ||
| props: {} | ||
| COMPOSED_OF: | ||
| from: Narrative | ||
| to: Frame | ||
| props: | ||
| weight: {type: number, required: false} | ||
| EXPRESSES: | ||
| from: Artifact | ||
| to: Frame | ||
| props: | ||
| confidence: {type: number, required: true} | ||
| method: {type: string, required: true} # classifier|rules|hybrid | ||
| provenance_id: {type: string, required: true} | ||
| MAKES: | ||
| from: Artifact | ||
| to: Claim | ||
| props: | ||
| confidence: {type: number, required: true} | ||
| span: {type: string, required: false} # stable pointer e.g., char offsets "120:184" | ||
| provenance_id: {type: string, required: true} | ||
| SUPPORTED_BY: | ||
| from: Frame | ||
| to: Assumption | ||
| props: | ||
| confidence: {type: number, required: true} | ||
| provenance_id: {type: string, required: true} | ||
| AMPLIFIED: | ||
| from: Community | ||
| to: Artifact | ||
| props: | ||
| weight: {type: number, required: false} | ||
| observed_ref: {type: string, required: false} | ||
| TRIGGERED_BY: | ||
| from: Narrative | ||
| to: Event | ||
| props: | ||
| confidence: {type: number, required: false} | ||
| provenance_id: {type: string, required: false} | ||
| DISPUTED_BY: | ||
| from: Claim | ||
| to: Evidence | ||
| props: | ||
| confidence: {type: number, required: false} | ||
| provenance_id: {type: string, required: false} | ||
| BROKEN_BY: | ||
| from: Assumption | ||
| to: Evidence | ||
| props: | ||
| confidence: {type: number, required: false} | ||
| provenance_id: {type: string, required: false} | ||
| HANDOFF_TO: | ||
| from: Narrative | ||
| to: Community | ||
| props: | ||
| handoff_score: {type: number, required: true} | ||
| from_tier: {type: string, required: false} | ||
| to_tier: {type: string, required: false} | ||
| observed_ref: {type: string, required: false} | ||
| provenance_id: {type: string, required: true} | ||
|
|
||
| indexes: | ||
| - label: Artifact | ||
| props: [artifact_id] | ||
| - label: Actor | ||
| props: [actor_id, handle] | ||
| - label: Narrative | ||
| props: [narrative_id, state] | ||
| - label: Frame | ||
| props: [frame_id, narrative_id] | ||
| - label: Assumption | ||
| props: [assumption_id] | ||
| - label: Claim | ||
| props: [claim_id] | ||
|
Comment on lines
+158
to
+170
Contributor
There was a problem hiding this comment. The indexes:
- label: Artifact
props: [artifact_id]
- label: Actor
props: [actor_id, handle]
- label: Narrative
props: [narrative_id, state]
- label: Frame
props: [frame_id, narrative_id]
- label: Assumption
props: [assumption_id]
- label: Claim
props: [claim_id]
- label: Community
props: [community_id]
- label: Event
props: [event_id]
- label: Evidence
props: [evidence_id] |
||
| constraints: | ||
| - type: unique | ||
| label: Artifact | ||
| prop: artifact_id | ||
| - type: unique | ||
| label: Actor | ||
| prop: actor_id | ||
| - type: unique | ||
| label: Narrative | ||
| prop: narrative_id | ||
| - type: unique | ||
| label: Frame | ||
| prop: frame_id | ||
| - type: unique | ||
| label: Claim | ||
| prop: claim_id | ||
| - type: unique | ||
| label: Assumption | ||
| prop: assumption_id | ||
| - type: unique | ||
| label: Community | ||
| prop: community_id | ||
| - type: unique | ||
| label: Event | ||
| prop: event_id | ||
| - type: unique | ||
| label: Evidence | ||
| prop: evidence_id | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,35 @@ | ||
| CREATE CONSTRAINT artifact_id_unique IF NOT EXISTS | ||
| FOR (a:Artifact) REQUIRE a.artifact_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT actor_id_unique IF NOT EXISTS | ||
| FOR (a:Actor) REQUIRE a.actor_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT narrative_id_unique IF NOT EXISTS | ||
| FOR (n:Narrative) REQUIRE n.narrative_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT frame_id_unique IF NOT EXISTS | ||
| FOR (f:Frame) REQUIRE f.frame_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT claim_id_unique IF NOT EXISTS | ||
| FOR (c:Claim) REQUIRE c.claim_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT assumption_id_unique IF NOT EXISTS | ||
| FOR (s:Assumption) REQUIRE s.assumption_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT community_id_unique IF NOT EXISTS | ||
| FOR (c:Community) REQUIRE c.community_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT event_id_unique IF NOT EXISTS | ||
| FOR (e:Event) REQUIRE e.event_id IS UNIQUE; | ||
|
|
||
| CREATE CONSTRAINT evidence_id_unique IF NOT EXISTS | ||
| FOR (e:Evidence) REQUIRE e.evidence_id IS UNIQUE; | ||
|
|
||
| CREATE INDEX actor_handle_idx IF NOT EXISTS | ||
| FOR (a:Actor) ON (a.handle); | ||
|
|
||
| CREATE INDEX narrative_state_idx IF NOT EXISTS | ||
| FOR (n:Narrative) ON (n.state); | ||
|
|
||
| CREATE INDEX frame_narrative_id_idx IF NOT EXISTS | ||
| FOR (f:Frame) ON (f.narrative_id); |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,47 @@ | ||
| CREATE TABLE IF NOT EXISTS narrative_run ( | ||
| run_id TEXT PRIMARY KEY, | ||
| created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(), | ||
| pipeline_version TEXT NOT NULL, | ||
| model_versions JSONB NOT NULL, | ||
| input_window_start TIMESTAMPTZ, | ||
| input_window_end TIMESTAMPTZ, | ||
| stamp_ref TEXT | ||
| ); | ||
|
|
||
| CREATE TABLE IF NOT EXISTS narrative_metric ( | ||
| run_id TEXT NOT NULL REFERENCES narrative_run(run_id), | ||
|
Contributor
There was a problem hiding this comment. To improve referential integrity, consider adding run_id TEXT NOT NULL REFERENCES narrative_run(run_id) ON DELETE CASCADE, |
||
| narrative_id TEXT NOT NULL, | ||
| metric_name TEXT NOT NULL, | ||
| metric_value DOUBLE PRECISION NOT NULL, | ||
| metric_dim JSONB, | ||
| PRIMARY KEY (run_id, narrative_id, metric_name) | ||
| ); | ||
|
|
||
| CREATE TABLE IF NOT EXISTS narrative_transition ( | ||
| run_id TEXT NOT NULL REFERENCES narrative_run(run_id), | ||
|
Contributor
There was a problem hiding this comment. For better referential integrity, it's advisable to add run_id TEXT NOT NULL REFERENCES narrative_run(run_id) ON DELETE CASCADE, |
||
| narrative_id TEXT NOT NULL, | ||
| from_state TEXT NOT NULL, | ||
| to_state TEXT NOT NULL, | ||
| rationale JSONB, | ||
| PRIMARY KEY (run_id, narrative_id, from_state, to_state) | ||
| ); | ||
|
|
||
| CREATE TABLE IF NOT EXISTS narrative_handoff ( | ||
| run_id TEXT NOT NULL REFERENCES narrative_run(run_id), | ||
|
Contributor
There was a problem hiding this comment. To maintain data consistency, please add run_id TEXT NOT NULL REFERENCES narrative_run(run_id) ON DELETE CASCADE, |
||
| narrative_id TEXT NOT NULL, | ||
| from_tier TEXT, | ||
| to_tier TEXT, | ||
| handoff_score DOUBLE PRECISION NOT NULL, | ||
| community_id TEXT, | ||
| provenance_id TEXT NOT NULL, | ||
| PRIMARY KEY (run_id, narrative_id, provenance_id) | ||
| ); | ||
|
|
||
| CREATE INDEX IF NOT EXISTS narrative_metric_narrative_idx | ||
| ON narrative_metric (narrative_id); | ||
|
|
||
| CREATE INDEX IF NOT EXISTS narrative_transition_narrative_idx | ||
| ON narrative_transition (narrative_id); | ||
|
|
||
| CREATE INDEX IF NOT EXISTS narrative_handoff_narrative_idx | ||
| ON narrative_handoff (narrative_id); | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The
spanproperty is currently defined as a generic string. To improve data validation and clarity, consider adding apatternto enforce a specific format, such as character offsets (e.g., '120:184'). Adescriptionwould also be helpful for consumers of the schema.