{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4YM7ODHJD6RBAY23J3MS7SWE2G","short_pith_number":"pith:4YM7ODHJ","canonical_record":{"source":{"id":"2501.10787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"586248602d0190536f8c851169434deb21e83c04cc729f5f386874b8f7b33363","abstract_canon_sha256":"81c45d69c47b204831780ec3e6b8870043882489110881b6aa2f31ef5781e52e"},"schema_version":"1.0"},"canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","source":{"kind":"arxiv","id":"2501.10787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10787","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10787v1","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10787","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"4YM7ODHJD6RB","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"4YM7ODHJD6RBAY23","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"4YM7ODHJ","created_at":"2026-07-05T10:02:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4YM7ODHJD6RBAY23J3MS7SWE2G","target":"record","payload":{"canonical_record":{"source":{"id":"2501.10787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"586248602d0190536f8c851169434deb21e83c04cc729f5f386874b8f7b33363","abstract_canon_sha256":"81c45d69c47b204831780ec3e6b8870043882489110881b6aa2f31ef5781e52e"},"schema_version":"1.0"},"canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:59.362211Z","signature_b64":"aC3AS7St4XI5o3JNqaiRI5NkocBOsn1t+id7HixB52s7oc53RL5Za3i86GIHMlVxZr8mypplRrO02LD5XwlsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","last_reissued_at":"2026-07-05T10:02:59.361688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:59.361688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.10787","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":"2026-07-05T10:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IIL2ENfTOMUVtkjGhhtNE/a/KklydZcsi0H72Vwq4MfLDhgnvn8WXSsvhFR7GsZgIHGu2LlNcZQUNrnZPyrPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:36:19.241788Z"},"content_sha256":"669707588275310a0e92d2f4c973c8a91497b109df092779992b68892c176f23","schema_version":"1.0","event_id":"sha256:669707588275310a0e92d2f4c973c8a91497b109df092779992b68892c176f23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4YM7ODHJD6RBAY23J3MS7SWE2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fan Zhou, Fuwei Zhang, Pengcheng Zhao, Shujin Lin, Zhixian He","submitted_at":"2025-01-18T14:54:56Z","abstract_excerpt":"Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information. However, existing methods face several issues: (1) Overlapping semantic information between different samples in the dataset hinders the model's multimodal aligning performance; (2) Existing models are not able to efficiently extract local features of the video; (3) T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10787","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/2501.10787/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":"2026-07-05T10:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vW/UrIjgD4gEgpSLCrZw5BJ91C7PDTVGlHWiCnVzxpqnbWVrjehxFzfuIN30Z7llS1PqksrJ5t8d+aAS90W6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:36:19.242310Z"},"content_sha256":"793d783342ca52ab53bd14b387e713999e0926c917d150a0b9d9a5055ba1f739","schema_version":"1.0","event_id":"sha256:793d783342ca52ab53bd14b387e713999e0926c917d150a0b9d9a5055ba1f739"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/bundle.json","state_url":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/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":"2026-08-15T18:36:19Z","links":{"resolver":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G","bundle":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/bundle.json","state":"https://pith.science/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YM7ODHJD6RBAY23J3MS7SWE2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4YM7ODHJD6RBAY23J3MS7SWE2G","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":"81c45d69c47b204831780ec3e6b8870043882489110881b6aa2f31ef5781e52e","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","title_canon_sha256":"586248602d0190536f8c851169434deb21e83c04cc729f5f386874b8f7b33363"},"schema_version":"1.0","source":{"id":"2501.10787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.10787","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2501.10787v1","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10787","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"4YM7ODHJD6RB","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"4YM7ODHJD6RBAY23","created_at":"2026-07-05T10:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"4YM7ODHJ","created_at":"2026-07-05T10:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:793d783342ca52ab53bd14b387e713999e0926c917d150a0b9d9a5055ba1f739","target":"graph","created_at":"2026-07-05T10:02:59Z","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/2501.10787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information. However, existing methods face several issues: (1) Overlapping semantic information between different samples in the dataset hinders the model's multimodal aligning performance; (2) Existing models are not able to efficiently extract local features of the video; (3) T","authors_text":"Fan Zhou, Fuwei Zhang, Pengcheng Zhao, Shujin Lin, Zhixian He","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10787","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":"sha256:669707588275310a0e92d2f4c973c8a91497b109df092779992b68892c176f23","target":"record","created_at":"2026-07-05T10:02:59Z","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":"81c45d69c47b204831780ec3e6b8870043882489110881b6aa2f31ef5781e52e","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-18T14:54:56Z","title_canon_sha256":"586248602d0190536f8c851169434deb21e83c04cc729f5f386874b8f7b33363"},"schema_version":"1.0","source":{"id":"2501.10787","kind":"arxiv","version":1}},"canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e619f70ce91fa210635b4ed92fcac4d1870bb77094e719e54195927e877c60e7","first_computed_at":"2026-07-05T10:02:59.361688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:59.361688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aC3AS7St4XI5o3JNqaiRI5NkocBOsn1t+id7HixB52s7oc53RL5Za3i86GIHMlVxZr8mypplRrO02LD5XwlsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:59.362211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.10787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:669707588275310a0e92d2f4c973c8a91497b109df092779992b68892c176f23","sha256:793d783342ca52ab53bd14b387e713999e0926c917d150a0b9d9a5055ba1f739"],"state_sha256":"b0680f8fc3d132af6da801c935403c327cc22e4c3a2adab134013208d34377d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvNz8fN8pafAdWDY/6EB4/31nCJERqtzKcYAh6Bt+0t3k/UNucZEEOaoBAUohLAWHr8gqYswKmdvWUnBsWcrDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:36:19.246027Z","bundle_sha256":"11220e737257ca6427207224c8dc9335d37971bf3a47f300f6e032bdacf97f59"}}