{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RZN66UIFODDE2OD2Y74D7J2AUV","short_pith_number":"pith:RZN66UIF","canonical_record":{"source":{"id":"2309.15086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"f85c6aa4b76667a73391e04f75c5f22b834ed7e9bc89418028c566621b50bdd1","abstract_canon_sha256":"d3e45977c87efd47ba820be0678be8ba451aef6634fc7b8ea3bd9399f3a94cb5"},"schema_version":"1.0"},"canonical_sha256":"8e5bef510570c64d387ac7f83fa740a5475b3bc5b8d5f76669a81216dddc2978","source":{"kind":"arxiv","id":"2309.15086","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15086","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15086v1","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15086","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"RZN66UIFODDE","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"RZN66UIFODDE2OD2","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"RZN66UIF","created_at":"2026-07-05T06:54:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RZN66UIFODDE2OD2Y74D7J2AUV","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"f85c6aa4b76667a73391e04f75c5f22b834ed7e9bc89418028c566621b50bdd1","abstract_canon_sha256":"d3e45977c87efd47ba820be0678be8ba451aef6634fc7b8ea3bd9399f3a94cb5"},"schema_version":"1.0"},"canonical_sha256":"8e5bef510570c64d387ac7f83fa740a5475b3bc5b8d5f76669a81216dddc2978","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:33.827713Z","signature_b64":"iVvLrw0ODBTBQ+/bKSeNi/6IsrowJXfiZQPh3K+Rgl54g0GaxLuZX0cIUjef1FgeIyrv2zpWHr3AphZVKsMaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5bef510570c64d387ac7f83fa740a5475b3bc5b8d5f76669a81216dddc2978","last_reissued_at":"2026-07-05T06:54:33.827218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:33.827218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15086","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0qCjwNPCQ8MCUmnf0SZHInvlsF/x0nw+Kl+Nzior14gLEF2Yv+928jB35gkMAe752489Qs29MwlJPf8M/T/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:49.837426Z"},"content_sha256":"d7e3fde731c14bf456057a502ea5de0fa76933a840fc4d38df0e95afab999cd5","schema_version":"1.0","event_id":"sha256:d7e3fde731c14bf456057a502ea5de0fa76933a840fc4d38df0e95afab999cd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RZN66UIFODDE2OD2Y74D7J2AUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-adverb retrieval with compositional adverb-action embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A. Sophia Koepke, Otniel-Bogdan Mercea, Thomas Hummel, Zeynep Akata","submitted_at":"2023-09-26T17:31:02Z","abstract_excerpt":"Retrieving adverbs that describe an action in a video poses a crucial step towards fine-grained video understanding. We propose a framework for video-to-adverb retrieval (and vice versa) that aligns video embeddings with their matching compositional adverb-action text embedding in a joint embedding space. The compositional adverb-action text embedding is learned using a residual gating mechanism, along with a novel training objective consisting of triplet losses and a regression target. Our method achieves state-of-the-art performance on five recent benchmarks for video-adverb retrieval. Furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15086","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.15086/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LU2ZPfQZZBnJRvVsu6dtEwI2YDp8eFh9s4y4u5mgdFJgNPSQN4WhsdgAMF8LaNUMqT0Eb5tqupCs5zrbo3gEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:30:49.845095Z"},"content_sha256":"75406ccb41c17fb16eeac2de98d6b0ce0bf745403fc784635f477c2d6b33b193","schema_version":"1.0","event_id":"sha256:75406ccb41c17fb16eeac2de98d6b0ce0bf745403fc784635f477c2d6b33b193"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZN66UIFODDE2OD2Y74D7J2AUV/bundle.json","state_url":"https://pith.science/pith/RZN66UIFODDE2OD2Y74D7J2AUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZN66UIFODDE2OD2Y74D7J2AUV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T17:30:49Z","links":{"resolver":"https://pith.science/pith/RZN66UIFODDE2OD2Y74D7J2AUV","bundle":"https://pith.science/pith/RZN66UIFODDE2OD2Y74D7J2AUV/bundle.json","state":"https://pith.science/pith/RZN66UIFODDE2OD2Y74D7J2AUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZN66UIFODDE2OD2Y74D7J2AUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RZN66UIFODDE2OD2Y74D7J2AUV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d3e45977c87efd47ba820be0678be8ba451aef6634fc7b8ea3bd9399f3a94cb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:31:02Z","title_canon_sha256":"f85c6aa4b76667a73391e04f75c5f22b834ed7e9bc89418028c566621b50bdd1"},"schema_version":"1.0","source":{"id":"2309.15086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15086","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15086v1","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15086","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"RZN66UIFODDE","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"RZN66UIFODDE2OD2","created_at":"2026-07-05T06:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"RZN66UIF","created_at":"2026-07-05T06:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:75406ccb41c17fb16eeac2de98d6b0ce0bf745403fc784635f477c2d6b33b193","target":"graph","created_at":"2026-07-05T06:54:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.15086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieving adverbs that describe an action in a video poses a crucial step towards fine-grained video understanding. We propose a framework for video-to-adverb retrieval (and vice versa) that aligns video embeddings with their matching compositional adverb-action text embedding in a joint embedding space. The compositional adverb-action text embedding is learned using a residual gating mechanism, along with a novel training objective consisting of triplet losses and a regression target. Our method achieves state-of-the-art performance on five recent benchmarks for video-adverb retrieval. Furth","authors_text":"A. Sophia Koepke, Otniel-Bogdan Mercea, Thomas Hummel, Zeynep Akata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:31:02Z","title":"Video-adverb retrieval with compositional adverb-action embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15086","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d7e3fde731c14bf456057a502ea5de0fa76933a840fc4d38df0e95afab999cd5","target":"record","created_at":"2026-07-05T06:54:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d3e45977c87efd47ba820be0678be8ba451aef6634fc7b8ea3bd9399f3a94cb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:31:02Z","title_canon_sha256":"f85c6aa4b76667a73391e04f75c5f22b834ed7e9bc89418028c566621b50bdd1"},"schema_version":"1.0","source":{"id":"2309.15086","kind":"arxiv","version":1}},"canonical_sha256":"8e5bef510570c64d387ac7f83fa740a5475b3bc5b8d5f76669a81216dddc2978","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e5bef510570c64d387ac7f83fa740a5475b3bc5b8d5f76669a81216dddc2978","first_computed_at":"2026-07-05T06:54:33.827218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:33.827218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iVvLrw0ODBTBQ+/bKSeNi/6IsrowJXfiZQPh3K+Rgl54g0GaxLuZX0cIUjef1FgeIyrv2zpWHr3AphZVKsMaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:33.827713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7e3fde731c14bf456057a502ea5de0fa76933a840fc4d38df0e95afab999cd5","sha256:75406ccb41c17fb16eeac2de98d6b0ce0bf745403fc784635f477c2d6b33b193"],"state_sha256":"758e9592111fde7e33c9aec303e6adeadcd8d73a5a242a31ebda67f1ec98e08f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a5EsrHg8S0wfAt4P7uBe5JKBothYbtDIo/rageIAXx3Z/AuF5twpbnoj1PjY5wF0Bjv5nl7cP/a665fEZBWTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:30:49.857913Z","bundle_sha256":"00427bd28efded2f719a1ae7151b02696a24833f41695909979761b7cd483a4b"}}