metaspn-entities 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

metaspn_entities/__init__.py

@@ -1,5 +1,7 @@
 from .adapter import SignalResolutionResult, resolve_normalized_social_signal
+from .attribution import OutcomeAttribution
 from .context import RecommendationContext, EntityContext, build_confidence_summary, build_recommendation_context
+from .demo import resolve_demo_social_identity
 from .events import EmittedEvent
 from .models import EntityResolution
 from .resolver import EntityResolver
@@ -8,6 +10,8 @@ from .sqlite_backend import SQLiteEntityStore
 __all__ = [
     "resolve_normalized_social_signal",
     "SignalResolutionResult",
+    "OutcomeAttribution",
+    "resolve_demo_social_identity",
     "EntityContext",
     "RecommendationContext",
     "build_confidence_summary",

metaspn_entities/attribution.py

@@ -0,0 +1,88 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple
+
+from .normalize import normalize_identifier
+
+
+@dataclass(frozen=True)
+class OutcomeAttribution:
+    entity_id: Optional[str]
+    confidence: float
+    matched_references: List[Dict[str, Any]] = field(default_factory=list)
+    strategy: str = "confidence-weighted-reference-v1"
+
+
+def normalize_outcome_references(references: Mapping[str, Any] | Sequence[Mapping[str, Any]]) -> List[Tuple[str, str]]:
+    refs: List[Tuple[str, str]] = []
+    if isinstance(references, Mapping):
+        for raw_type in sorted(references):
+            value = references[raw_type]
+            if value is None:
+                continue
+            if isinstance(value, str) and value.strip():
+                refs.append((str(raw_type), value.strip()))
+        return refs
+
+    for item in references:
+        id_type = str(item.get("identifier_type") or item.get("type") or "").strip()
+        value = str(item.get("value") or "").strip()
+        if not id_type or not value:
+            continue
+        refs.append((id_type, value))
+    return refs
+
+
+def rank_entity_candidates(
+    references: Iterable[Tuple[str, str]],
+    resolve_reference: Any,
+) -> OutcomeAttribution:
+    candidate_scores: Dict[str, float] = {}
+    candidate_hits: Dict[str, int] = {}
+    matched: List[Dict[str, Any]] = []
+    total_refs = 0
+
+    for identifier_type, value in references:
+        total_refs += 1
+        match = resolve_reference(identifier_type, value)
+        matched.append(
+            {
+                "identifier_type": identifier_type,
+                "value": value,
+                "normalized_value": match.get("normalized_value"),
+                "matched_entity_id": match.get("entity_id"),
+                "reference_confidence": float(match.get("confidence", 0.0)),
+            }
+        )
+        entity_id = match.get("entity_id")
+        confidence = float(match.get("confidence", 0.0))
+        if entity_id:
+            candidate_scores[entity_id] = candidate_scores.get(entity_id, 0.0) + confidence
+            candidate_hits[entity_id] = candidate_hits.get(entity_id, 0) + 1
+
+    if not candidate_scores:
+        return OutcomeAttribution(entity_id=None, confidence=0.0, matched_references=matched)
+
+    ranked = sorted(
+        candidate_scores.items(),
+        key=lambda kv: (
+            -kv[1],
+            -candidate_hits.get(kv[0], 0),
+            kv[0],
+        ),
+    )
+    best_entity_id, best_score = ranked[0]
+    denom = max(1, total_refs)
+    normalized_confidence = min(1.0, round(best_score / float(denom), 6))
+    return OutcomeAttribution(
+        entity_id=best_entity_id,
+        confidence=normalized_confidence,
+        matched_references=matched,
+    )
+
+
+def normalize_reference(identifier_type: str, value: str) -> Tuple[str, str]:
+    if identifier_type == "entity_id":
+        return identifier_type, value
+    return identifier_type, normalize_identifier(identifier_type, value)

metaspn_entities/demo.py

@@ -0,0 +1,81 @@
+from __future__ import annotations
+
+from typing import Any, Dict, Mapping
+
+from .models import EntityType
+from .resolver import EntityResolver
+
+
+def resolve_demo_social_identity(
+    resolver: EntityResolver,
+    social_payload: Mapping[str, Any],
+    *,
+    caused_by: str = "demo-pipeline",
+) -> Dict[str, Any]:
+    platform = str(social_payload.get("platform") or "").strip().lower()
+    source = str(social_payload.get("source") or social_payload.get("provenance") or "demo")
+
+    handle = social_payload.get("author_handle") or social_payload.get("handle")
+    if not isinstance(handle, str) or not handle.strip():
+        raise ValueError("demo payload requires author_handle or handle")
+    handle = handle.strip()
+
+    handle_type = f"{platform}_handle" if platform else "handle"
+    resolution = resolver.resolve(
+        handle_type,
+        handle,
+        context={
+            "entity_type": EntityType.PERSON,
+            "caused_by": caused_by,
+            "provenance": source,
+            "confidence": 0.93,
+        },
+    )
+
+    for key in ("profile_url", "author_url", "canonical_url"):
+        url = social_payload.get(key)
+        if isinstance(url, str) and url.strip():
+            resolver.add_alias(
+                resolution.entity_id,
+                "canonical_url",
+                url.strip(),
+                confidence=0.96,
+                caused_by=caused_by,
+                provenance=source,
+            )
+            break
+
+    email = social_payload.get("email")
+    if isinstance(email, str) and email.strip():
+        resolver.add_alias(
+            resolution.entity_id,
+            "email",
+            email.strip(),
+            confidence=0.98,
+            caused_by=caused_by,
+            provenance=source,
+        )
+
+    canonical_id = resolver.store.canonical_entity_id(resolution.entity_id)
+    context = resolver.entity_context(canonical_id)
+    digest_payload = {
+        "entity_id": canonical_id,
+        "confidence": context.confidence_summary["overall_confidence"],
+        "matched_identifiers": [
+            {
+                "identifier_type": item["identifier_type"],
+                "value": item["value"],
+                "confidence": item["confidence"],
+                "last_seen_at": item["last_seen_at"],
+            }
+            for item in context.identifiers
+        ],
+        "why": {
+            "matched_identifier_count": len(context.identifiers),
+            "alias_count": len(context.aliases),
+            "confidence_summary": context.confidence_summary,
+            "relationship_stage_hint": resolver.recommendation_context(canonical_id).relationship_stage_hint,
+        },
+        "events": [event.payload for event in resolver.drain_events()],
+    }
+    return digest_payload

metaspn_entities/normalize.py

@@ -7,7 +7,17 @@ def normalize_identifier(identifier_type: str, value: str) -> str:
     identifier_type = identifier_type.strip().lower()
     value = value.strip()
 
-    if identifier_type in {"twitter_handle", "github_handle", "handle"}:
+    if identifier_type in {
+        "twitter_handle",
+        "x_handle",
+        "linkedin_handle",
+        "github_handle",
+        "instagram_handle",
+        "tiktok_handle",
+        "bluesky_handle",
+        "youtube_handle",
+        "handle",
+    }:
         return value.lstrip("@").lower()
 
     if identifier_type == "email":

metaspn_entities/resolver.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from typing import Any, Dict, List, Optional
 
+from .attribution import OutcomeAttribution, normalize_outcome_references, normalize_reference, rank_entity_candidates
 from .context import RecommendationContext, EntityContext, build_confidence_summary, build_recommendation_context
 from .events import EmittedEvent, EventFactory
 from .models import (
@@ -166,6 +167,34 @@ class EntityResolver:
         identifiers = self.store.list_identifier_records_for_entity(canonical_id)
         return build_recommendation_context(canonical_id, aliases, identifiers)
 
+    def attribute_outcome(self, references: Any) -> OutcomeAttribution:
+        refs = normalize_outcome_references(references)
+
+        def _resolve_ref(identifier_type: str, value: str) -> Dict[str, Any]:
+            raw_type, normalized = normalize_reference(identifier_type, value)
+            if raw_type == "entity_id":
+                entity = self.store.get_entity(normalized)
+                if not entity:
+                    return {"entity_id": None, "confidence": 0.0, "normalized_value": normalized}
+                return {
+                    "entity_id": self.store.canonical_entity_id(str(entity["entity_id"])),
+                    "confidence": 0.99,
+                    "normalized_value": normalized,
+                }
+
+            alias = self.store.find_alias(raw_type, normalized)
+            if not alias:
+                return {"entity_id": None, "confidence": 0.0, "normalized_value": normalized}
+
+            canonical = self.store.canonical_entity_id(str(alias["entity_id"]))
+            identifier = self.store.get_identifier(raw_type, normalized)
+            alias_conf = float(alias["confidence"])
+            identifier_conf = float(identifier["confidence"]) if identifier else 0.0
+            confidence = round(max(alias_conf, identifier_conf), 6)
+            return {"entity_id": canonical, "confidence": confidence, "normalized_value": normalized}
+
+        return rank_entity_candidates(refs, _resolve_ref)
+
     def export_snapshot(self, output_path: str) -> None:
         self.store.export_snapshot(output_path)
 

metaspn_entities/sqlite_backend.py

@@ -103,6 +103,12 @@ class SQLiteEntityStore:
             (identifier_type, normalized_value),
         ).fetchone()
 
+    def get_identifier(self, identifier_type: str, normalized_value: str) -> Optional[sqlite3.Row]:
+        return self.conn.execute(
+            "SELECT * FROM identifiers WHERE identifier_type = ? AND normalized_value = ?",
+            (identifier_type, normalized_value),
+        ).fetchone()
+
     def upsert_identifier(
         self,
         identifier_type: str,

{metaspn_entities-0.1.6.dist-info → metaspn_entities-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metaspn-entities
-Version: 0.1.6
+Version: 0.1.8
 Summary: Canonical entity resolution, aliasing, and merges for MetaSPN systems
 Author: MetaSPN Contributors
 License-Expression: MIT
@@ -122,3 +122,29 @@ The recommendation context includes:
 - preferred channel hint
 - relationship stage hint (`cold` / `warm` / `engaged`)
 - merge-safe continuity fields keyed to canonical entity IDs
+
+## M3 Outcome Attribution API
+
+Outcome evaluators can map attempt/outcome references back to canonical entity lineage:
+
+- `resolver.attribute_outcome(references)`
+
+Supported references include `entity_id`, `email`, `canonical_url`, handles, domains, and names.
+
+Attribution guarantees:
+- canonical merge redirects are resolved before returning `entity_id`
+- output includes explicit confidence for downstream learning logic
+- deterministic tie-breaks are applied by score, then hit count, then entity ID
+
+## Demo Pipeline Invocation
+
+For demo digest identity resolution (without direct DB queries in renderer), use:
+
+- `resolve_demo_social_identity(resolver, social_payload)`
+
+Returned payload includes:
+- `entity_id`
+- `confidence`
+- `matched_identifiers`
+- `why` metadata (confidence summary, counts, relationship hint)
+- emitted event payloads for auditability

metaspn_entities-0.1.8.dist-info/RECORD

@@ -0,0 +1,15 @@
+metaspn_entities/__init__.py,sha256=mkKm_bGmH4PogzvMUR_BJDuuOSFBkz-VvWzs1Bie06Y,792
+metaspn_entities/adapter.py,sha256=eNB5kr1tinav85WPA4YCldRDJBgb6uYe3ZWCRVjdOms,4654
+metaspn_entities/attribution.py,sha256=bCJGAW5XAzI9ZOWVTvw_bWfUVXbEAATFJ3N9W4_C2U8,3061
+metaspn_entities/context.py,sha256=sUpW50Z99R0iQ5ryVR9uk7WqUaiKCxMyTQlvuV3DvVk,6054
+metaspn_entities/demo.py,sha256=QJyIRuds0AoOwGBo0a93f62742848v4XogSV99LQjL0,2764
+metaspn_entities/events.py,sha256=Hkc3gy5_vRTSR0MKUvF24dTqNqOkG423_PTUe7csUfw,2066
+metaspn_entities/models.py,sha256=b2EFsc1EIT9Ao_bKA2I52-5W_0fTwhsyO6VFRG8gZg8,1377
+metaspn_entities/normalize.py,sha256=o05fEXXoDWAGH1RNEH_zcfhRxR6CpAEBralbTlsK5ng,1308
+metaspn_entities/resolver.py,sha256=bKnxInPNLefdgblrrl1oAtc2aiUlXqZz3bmSZWNX21E,9910
+metaspn_entities/sqlite_backend.py,sha256=h7_dMNmd9-k9hxvJwZp_TM9_yNWyFbJric6TvH_BseU,12087
+metaspn_entities-0.1.8.dist-info/licenses/LICENSE,sha256=tvVpto97dUnh1-KVYPs1rCr5dzyX8jUyNmT7F7ZPVAM,1077
+metaspn_entities-0.1.8.dist-info/METADATA,sha256=AD2i7hlPWzTu0DeoWO1zbaHS2zIknbc8x_qeolStghM,4995
+metaspn_entities-0.1.8.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+metaspn_entities-0.1.8.dist-info/top_level.txt,sha256=YP2V8Z1Statrs3YAI-tGvyC73vLjPHr9Vkal4yqXkhs,17
+metaspn_entities-0.1.8.dist-info/RECORD,,

metaspn_entities-0.1.6.dist-info/RECORD

@@ -1,13 +0,0 @@
-metaspn_entities/__init__.py,sha256=aija_xk40mk4JreYPiKKIpKwt6eQdUQRlrriwNkgZB0,639
-metaspn_entities/adapter.py,sha256=eNB5kr1tinav85WPA4YCldRDJBgb6uYe3ZWCRVjdOms,4654
-metaspn_entities/context.py,sha256=sUpW50Z99R0iQ5ryVR9uk7WqUaiKCxMyTQlvuV3DvVk,6054
-metaspn_entities/events.py,sha256=Hkc3gy5_vRTSR0MKUvF24dTqNqOkG423_PTUe7csUfw,2066
-metaspn_entities/models.py,sha256=b2EFsc1EIT9Ao_bKA2I52-5W_0fTwhsyO6VFRG8gZg8,1377
-metaspn_entities/normalize.py,sha256=nPAHRfipgS6zHy2x70ZFd5HB1W4FKmeTF8Kd4TYz5tI,1125
-metaspn_entities/resolver.py,sha256=lmjQj5W2ny1_FnzNB-_cywReL_5ScOOHohV_TcY4usM,8345
-metaspn_entities/sqlite_backend.py,sha256=Ed0CGAfDGlzKuD-v3xkxumGf8My4WByMQRtrO9JHK84,11790
-metaspn_entities-0.1.6.dist-info/licenses/LICENSE,sha256=tvVpto97dUnh1-KVYPs1rCr5dzyX8jUyNmT7F7ZPVAM,1077
-metaspn_entities-0.1.6.dist-info/METADATA,sha256=Lp2AXFXLhnY46SlExYN4pnqora7_DH9wcwF5IAMuOD0,4130
-metaspn_entities-0.1.6.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-metaspn_entities-0.1.6.dist-info/top_level.txt,sha256=YP2V8Z1Statrs3YAI-tGvyC73vLjPHr9Vkal4yqXkhs,17
-metaspn_entities-0.1.6.dist-info/RECORD,,