{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:54A4BSN2RCNWMGLYB2XH27DMFN","short_pith_number":"pith:54A4BSN2","canonical_record":{"source":{"id":"2312.06462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T15:51:38Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2709262739ca7d89189fa133516aa00bbe8268516df9eaed5c96096c18c4e16f","abstract_canon_sha256":"8f7edacff7b9e11e611289cf196e62a3945bd257c106179661a819f69f927679"},"schema_version":"1.0"},"canonical_sha256":"ef01c0c9ba889b6619780eae7d7c6c2b736f05a09312e17573a122dd01094094","source":{"kind":"arxiv","id":"2312.06462","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06462","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06462v2","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06462","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"54A4BSN2RCNW","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"54A4BSN2RCNWMGLY","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"54A4BSN2","created_at":"2026-07-05T08:05:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:54A4BSN2RCNWMGLYB2XH27DMFN","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T15:51:38Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2709262739ca7d89189fa133516aa00bbe8268516df9eaed5c96096c18c4e16f","abstract_canon_sha256":"8f7edacff7b9e11e611289cf196e62a3945bd257c106179661a819f69f927679"},"schema_version":"1.0"},"canonical_sha256":"ef01c0c9ba889b6619780eae7d7c6c2b736f05a09312e17573a122dd01094094","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:06.856168Z","signature_b64":"jZM1dtAVt3zBRYR+ZB8IruyfWhPGQetsKOHfjpz7mD7OjXS4FcexjVbwaHg7LfLUQE5Ays6p46C7/D3H6FVdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef01c0c9ba889b6619780eae7d7c6c2b736f05a09312e17573a122dd01094094","last_reissued_at":"2026-07-05T08:05:06.855666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:06.855666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06462","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzzUpOX5K2zQNbdd3B9MTlrRa0rhjuU2qUmE4FAOdv2KOcHxrUu3gTRMafK15t5Pii2v/Yqha3vPKrs/itMhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:20:18.066013Z"},"content_sha256":"3378ced81a5e1d701fbd59a56b148d79064ad400702bc20bf26f8e8b5fa92a7b","schema_version":"1.0","event_id":"sha256:3378ced81a5e1d701fbd59a56b148d79064ad400702bc20bf26f8e8b5fa92a7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:54A4BSN2RCNWMGLYB2XH27DMFN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Cheng Zhen, Pengfei Gao, Pengfei Yan, Qi Yang, Shiming Xiang, Tong Li, Xing Nie, Ying Guo","submitted_at":"2023-12-11T15:51:38Z","abstract_excerpt":"Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06462","kind":"arxiv","version":2},"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/2312.06462/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":"2026-07-05T08:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUOMxRxl4tKIbDtV/cRz1fNr65/pXFgApOE7qi5r53lOQwhL3PKPfZ+mn7ofs8Vb4lX5ZbAtrP8lN6J9o8SCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:20:18.066525Z"},"content_sha256":"92063d0d709a3b12826cb62dc757b4035216e0fa39bb2d4a6b1421f359ecaf9e","schema_version":"1.0","event_id":"sha256:92063d0d709a3b12826cb62dc757b4035216e0fa39bb2d4a6b1421f359ecaf9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54A4BSN2RCNWMGLYB2XH27DMFN/bundle.json","state_url":"https://pith.science/pith/54A4BSN2RCNWMGLYB2XH27DMFN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54A4BSN2RCNWMGLYB2XH27DMFN/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":"2026-08-17T22:20:18Z","links":{"resolver":"https://pith.science/pith/54A4BSN2RCNWMGLYB2XH27DMFN","bundle":"https://pith.science/pith/54A4BSN2RCNWMGLYB2XH27DMFN/bundle.json","state":"https://pith.science/pith/54A4BSN2RCNWMGLYB2XH27DMFN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54A4BSN2RCNWMGLYB2XH27DMFN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:54A4BSN2RCNWMGLYB2XH27DMFN","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":"8f7edacff7b9e11e611289cf196e62a3945bd257c106179661a819f69f927679","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T15:51:38Z","title_canon_sha256":"2709262739ca7d89189fa133516aa00bbe8268516df9eaed5c96096c18c4e16f"},"schema_version":"1.0","source":{"id":"2312.06462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06462","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06462v2","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06462","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"54A4BSN2RCNW","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"54A4BSN2RCNWMGLY","created_at":"2026-07-05T08:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"54A4BSN2","created_at":"2026-07-05T08:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:92063d0d709a3b12826cb62dc757b4035216e0fa39bb2d4a6b1421f359ecaf9e","target":"graph","created_at":"2026-07-05T08:05:06Z","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/2312.06462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglem","authors_text":"Cheng Zhen, Pengfei Gao, Pengfei Yan, Qi Yang, Shiming Xiang, Tong Li, Xing Nie, Ying Guo","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T15:51:38Z","title":"Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06462","kind":"arxiv","version":2},"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":"sha256:3378ced81a5e1d701fbd59a56b148d79064ad400702bc20bf26f8e8b5fa92a7b","target":"record","created_at":"2026-07-05T08:05:06Z","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":"8f7edacff7b9e11e611289cf196e62a3945bd257c106179661a819f69f927679","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T15:51:38Z","title_canon_sha256":"2709262739ca7d89189fa133516aa00bbe8268516df9eaed5c96096c18c4e16f"},"schema_version":"1.0","source":{"id":"2312.06462","kind":"arxiv","version":2}},"canonical_sha256":"ef01c0c9ba889b6619780eae7d7c6c2b736f05a09312e17573a122dd01094094","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef01c0c9ba889b6619780eae7d7c6c2b736f05a09312e17573a122dd01094094","first_computed_at":"2026-07-05T08:05:06.855666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:06.855666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZM1dtAVt3zBRYR+ZB8IruyfWhPGQetsKOHfjpz7mD7OjXS4FcexjVbwaHg7LfLUQE5Ays6p46C7/D3H6FVdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:06.856168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3378ced81a5e1d701fbd59a56b148d79064ad400702bc20bf26f8e8b5fa92a7b","sha256:92063d0d709a3b12826cb62dc757b4035216e0fa39bb2d4a6b1421f359ecaf9e"],"state_sha256":"398771d291bdd2bf0e8f33559584b409b4f83ae3c18c11bf01f9e261bdb26a6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FV6n1wAeyZpdS/UOEQC8wUHpGXiYP7LR9uW3PpwWOcjbWdgKpUbDSzHgTuVythCWQSDibs5eChUXo9C0EnjZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:20:18.071713Z","bundle_sha256":"0ef6eb4b2a384b042d418f9d56da38bf1f64dbcb96b036dfbb8bdca95f057fb3"}}